This paper investigates purchasing-power parity (PPP) since the late nineteenth century. I collected data for a group of twenty countries over 100 years, a larger historical panel of annual data than has ever been studied. The evidence for long-run PPP is favorable using recent multivariate and univariate tests of higher power. Residual variance analysis shows that episodes of floating exchange rates have generally been associated with larger deviations from PPP, as expected; this result is not attributable to significantly greater persistence (longer half-lives) of deviations in such regimes, but is due to the larger shocks to the real exchange rate process in such episodes. In the course of the twentieth century, there was relatively little change in the capacity of international market integration to smooth out real exchange rate shocks. Instead, changes in the size of shocks depended on the political economy of monetary and exchange rate regime choice under the constraints imposed by the trilemma.